HippoSpark: An On-Demand Experience System for LLM Reasoning
On the map: LLM reasoning → Test-time compute and efficient thinking
Abstract (arXiv)
Distilling historical trajectories into reusable experience to enhance future problem-solving has become a focal point of recent LLM research. However, existing methods predominantly operate at the task level, leveraging general summaries or rules under the assumption that analogous tasks share universal solution patterns. This approach often fails in complex reasoning, which typically falters at local bottlenecks that require precise, state-specific guidance rather than broad heuristics. We introduce HippoSpark, a state-level experience system that performs on-demand retrieval tailored to the immediate needs of the current reasoning state. Across mathematical, scientific, and programming benchmarks, HippoSpark consistently outperforms both standard prompting and task-level experience baselines. Our findings reveal that the most effective experience systems are those that provide actionable guidance at critical bottlenecks rather than serving as generic task-level context. Our code is available at https://github.com/DanlingMeng/HippoSpark.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 6 of its 38 references that are in the map. First posted on arXiv 29 Jun 2026.
Builds on
6 of 38 references.
References · 6
- 2025Qwen3 Technical Reportcited by 8,820
- 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
- 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 284
- 2025EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecyclecited by 137
- 2025Memp: Exploring Agent Procedural Memorycited by 103
- 2025Get Experience from Practice: LLM Agents with Record & Replaycited by 23
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Beyond Experience Retrieval: Learning to Generate Utility-Optimized Structured Experience for Frozen LLMs
- 2025Rethinking the Unsolvable: When In-Context Search Meets Test-Time Scaling
- 2025Prompting Test-Time Scaling Is A Strong LLM Reasoning Data Augmentation
- 2025Can Past Experience Accelerate LLM Reasoning?
- 2026Procedural Knowledge at Scale Improves Reasoning
- 2026Self-Verification Dilemma: Experience-Driven Suppression of Overused Checking in LLM Reasoning
- 2026Decocted Experience Improves Test-Time Inference in LLM Agents
- 2026Not Too Hard, Not Too Easy: Learning from Intermediate States for LLM Structured Reasoning